Ornith-1.5: Self-Improving Open-Source MoE Models Rival Claude Opus
aftahi_ai · x · 2026-08-19
Ornith-1.5 is a family of open-source LLMs (9B Dense, 35B MoE, 397B MoE) released under the MIT license. It trains via end-to-end self-improvement strategies, enabling the model to propose tasks, generate scaffolds, and use experiences for reinforcement learning.
It achieves state-of-the-art performance among comparable open-source models:
- Terminal-Bench 2.1: 86.1
- SWE-Bench (verified): 86
- DeepSWE: 56
- HLE: 44.6
Its performance in reasoning, agentic, and coding tasks is claimed to be comparable to Claude Opus 4.8.
More from coding & agent
- Bolt Slides: Build presentation decks with live web apps via a single prompt — tom_doerr · 2026-08-20
- PSAISuite: Turning PowerShell into a Multi-Model Agent Runtime — dfinke · 2026-08-20
- LangChain Webinar: Towards Automating Eval & Environment Engineering for Agents — LangChain · 2026-08-20
- LEGO-RL: harness-native reinforcement learning for coding agents — Lego-X · 2026-08-20
- OJO Review: Bridging the Gap Between Demos and Shippable Products — kimmonismus · 2026-08-20
- Vercel Engineering: Using AI to Set Transactional Email Guidelines — JohnPhamous · 2026-08-20